基于B-样条曲线暗通道的图像去雾算法

doi:10.19678/j.issn.1000-3428.0063307

摘要/Abstract

摘要： 针对暗原色去雾算法在高亮背景图像中出现光晕（Halo）效应的问题，提出一种基于B-样条曲线加gamma（γ）修正透射率去除Halo效应的算法。通过分析暗原色透射率图像的统计直方图，得出Halo效应的产生是由于HE算法透射率直方图中低灰度值占比较大，因此需要对直方图低灰度包络进行修正。寻找直方图中第1个低灰度波峰，在2个波谷间进行子区间分割，并以区间边界点作为样条区间节点计算三次样条曲线，以拟合低灰度包络。基于透射率图中修正位置对修正结果的关键性作用，采用改进的大津法从横向和纵向两个维度对透射率图进行分割，以确定修正区域，实现精准补偿，提高抗噪性能。根据不同雾图选择合适的γ修正系数修正拟合的灰度包络并对图像进行还原，验证不同修正系数对结果的影响。实验结果表明，当修正系数γ>1.5时，Halo效应能被有效减缓或消除，与HE算法相比，该算法的对比度、信息熵最大可分别提高10.1%和9.9%，算法并行度可达到M或N级。

关键词: 图像去雾, B-样条, 暗原色, 透射率, γ修正

Abstract: A modified algorithm for transmitting Halo removal based on the B-spline curve and gamma (γ) correction is proposed to solve the Halo effect of dark primary color defogging algorithm in bright background images.First, the statistical histogram of the dark primary color transmission image is plotted.It is known from the data that the halo effect is induced by the extremely high proportion of low gray transmission, so the low gray envelope of the histogram required modification.Hence, the first gray peak in the histogram is searched, and subinterval segmentation between the two valleys is conducted.The cubic spline curve is determined with the interval boundary points as spline interval nodes to fit the low gray envelope.Second, the position of correction in the transmission map plays a significant role in the results, and it is necessary to separate the area to be corrected from the transmission map.The improved Otsu method is then used to segment the transmission map from the horizontal and vertical dimensions to determine the correction area and improve the antinoise performance.Third, appropriate correction coefficients are selected based on different fog maps to modify the gray envelope and restore the image to verify the effects of different parameters.The experimental results show that the Halo effect can be suppressed or eliminated when the correction coefficient γ>1.5.Compared with the HE algorithm, the contrast and information entropy of this algorithm can be improved by 10.1% and 9.9%, respectively, and the algorithm parallelism can reach the M or N level.

Key words: image defogging, B-spline, Dark Primary Color(DCP), transmissivity, γ correction

中图分类号:

TP391.41

温立民, 巨永锋, 王会峰, 徐娟. 基于B-样条曲线暗通道的图像去雾算法[J]. 计算机工程, 2022, 48(11): 215-223.

WEN Limin, JU Yongfeng, WANG Huifeng, XU Juan. Image Defogging Algorithm Based on B-Spline Curve Dark Channel[J]. Computer Engineering, 2022, 48(11): 215-223.

https://www.ecice06.com/CN/Y2022/V48/I11/215

图/表 10

20230221175052

20230221175058

20230221175123

20230221175126

20230221175129

20230221175132

20230221175135

20230221175139

20230221175142

20230221175146

参考文献

[1] 禹晶, 徐东彬, 廖庆敏.图像去雾技术研究进展[J].中国图象图形学报, 2011, 16(9):1561-1576. YU J, XU D B, LIAO Q M.Image defogging:a survey[J].Journal of Image and Graphics, 2011, 16(9):1561-1576.(in Chinese)
[2] 孙启隆, 于萍, 司振惠, 等.基于暗通道的沙尘图像增强算法[J].吉林大学学报(理学版), 2021, 59(5):1179-1187. SUN Q L, YU P, SI Z H, et al.Dust image enhancement algorithm based on dark channel[J].Journal of Jilin University(Science Edition), 2021, 59(5):1179-1187.(in Chinese)
[3] 涂刚, 刘华清, 朱昌平.一种改进的自适应非局部均值图像去噪方法[J].控制工程, 2016, 23(6):839-843. TU G, LIU H Q, ZHU C P.An improved adaptive non-local mean image denoising method[J].Control Engineering of China, 2016, 23(6):839-843.(in Chinese)
[4] 潘磊, 郑益军.基于多尺度图像融合的单幅图像去雾算法[J].计算机工程, 2016, 42(8):255-260. PAN L, ZHENG Y J.Single image dehazing algorithm based on multi-scale image fusion[J].Computer Engineering, 2016, 42(8):255-260.(in Chinese)
[5] LIU W, HOU X X, DUAN J, et al.End-to-end single image fog removal using enhanced cycle consistent adversarial networks[J].IEEE Transactions on Image Processing, 2020, 29:7819-7833.
[6] 李硕士, 刘洪瑞, 甘永东, 等.基于残差密集块与注意力机制的图像去雾网络[J].湖南大学学报(自然科学版), 2021, 48(6):112-118. LI S S, LIU H R, GAN Y D, et al.Image dehazing network based on residual dense block and attention mechanism[J].Journal of Hunan University (Natural Sciences), 2021, 48(6):112-118.(in Chinese)
[7] SCHECHNER Y Y, NARASIMHAN S G, NAYAR S K.Instant dehazing of images using polarization[C]//Proceedings of 2001 IEEE Computer Society Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2001:325-332.
[8] NARASIMHAN S G, NAYAR S K.Contrast restoration of weather degraded images[J].IEEE Transactions on Pattern Analysis and Machine Intelligence, 2003, 25(6):713-724.
[9] HE K M, SUN J, TANG X O.Single image haze removal using dark channel prior[C]//Proceedings of IEEE Conference on Computer Vision and Pattern Recognition.Washington D.C., USA:IEEE Press, 2009:1956-1963.
[10] 张霓, 曾乐襄, 何熊熊, 等.基于滚动时域粒子群优化的视频去雾算法[J].控制与决策, 2021(9):2218-2224. ZHANG N, ZENG L X, HE X X, et al.Receding horizon particle swarm optimization based video defogging algorithm[J].Control and Decision, 2021(9):2218-2224.(in Chinese)
[11] FANG Z, WU Q L, HUANG D R, et al.An improved DCP based image defogging algorithm combined with adaptive fusion strategy[J].Mathematical Problems in Engineering, 2021, 47(11):1-13.
[12] 周文舟, 范晨, 胡小平, 等.多尺度奇异值分解的偏振图像融合去雾算法与实验[J].中国光学, 2021, 14(2):298-306. ZHOU W Z, FAN C, HU X P, et al.Multi-scale singular value decomposition polarization image fusion defogging algorithm and experiment[J].Chinese Optics, 2021, 14(2):298-306.(in Chinese)
[13] 段镖, 李靖, 陈怀民, 等.一种新的夜间单图像去雾方法[J].西北工业大学学报, 2021, 39(3):604-610. DUAN B, LI J, CHEN H M, et al.New approach to dehaze single nighttime image[J].Journal of Northwestern Polytechnical University, 2021, 39(3):604-610.(in Chinese)
[14] 高涛, 刘梦尼, 陈婷, 等.结合暗亮通道先验的远近景融合去雾算法[J].西安交通大学学报, 2021, 55(10):78-86. GAO T, LIU M N, CHEN T, et al.A far and near scene fusion defogging algorithm based on the prior of dark-light channel[J].Journal of Xi'an Jiaotong University, 2021, 55(10):78-86.(in Chinese)
[15] WANG X, ZHANG X, ZHU H C, et al.An effective algorithm for single image fog removal[J].Mobile Networks and Applications, 2021, 26(3):1250-1258.
[16] KUMAR R, BALASUBRAMANIAN R, KAUSHIK B K.Efficient method and architecture for real-time video defogging[J].IEEE Transactions on Intelligent Transportation Systems, 2021, 22(10):6536-6546.
[17] 金仙力, 张威, 刘林峰.基于引导滤波和自适应容差的图像去雾算法[J].通信学报, 2020(5):27-36. JIN X L, ZHANG W, LIU L F.Image defogging algorithm based on guided filtering and adaptive tolerance[J].Journal on Communications, 2020(5):27-36.(in Chinese)
[18] 高银, 云利军, 石俊生, 等.基于TV模型的暗原色理论雾天图像复原算法[J].中国激光, 2015, 42(8):281-286. GAO Y, YUN L J, SHI J S, et al.Enhancement dark channel algorithm of fog image based on the TV model[J].Chinese Journal of Lasers, 2015, 42(8):281-286.(in Chinese)
[19] 温立民, 巨永锋, 闫茂德.基于自然统计特征分布的交通图像雾浓度检测[J].电子学报, 2017, 45(8):1888-1895. WEN L M, JU Y F, YAN M D.Inspection of fog density for traffic image based on distribution characteristics of natural statistics[J].Acta Electronica Sinica, 2017, 45(8):1888-1895.(in Chinese)
[20] 姬佩佩, 张贵仓, 汪凯, 等.基于全正基的非均匀三次加权B样条[J].中国图象图形学报, 2021, 26(4):939-951. JI P P, ZHANG G C, WANG K, et al.Non uniform weighted cubic B-spline based on all positive basis[J].Journal of Image and Graphics, 2021, 26(4):939-951.(in Chinese)
[21] 陈良骥, 高飞, 赵波, 等.曲率自适应条件下特征点选取的非均匀B样条曲线插值方法[J].计算机辅助设计与图形学学报, 2021, 33(9):1377-1387. CHEN L J, GAO F, ZHAO B, et al.Non-uniform B-spline curve interpolation method for feature points selection under curvature adaptive condition[J].Journal of Computer-Aided Design & Computer Graphics, 2021, 33(9):1377-1387.(in Chinese)
[22] ANCUTI C O, ANCUTI C.Single image dehazing by multi-scale fusion[J].IEEE Transactions on Image Processing, 2013, 22(8):3271-3282.
[23] HAUTIÈRE N, TAREL J P, HALMAOUI H, et al.Enhanced fog detection and free-space segmentation for car navigation[J].Machine Vision and Applications, 2014, 25(3):667-679.
[24] 侯英伟, 宋玉收, 孙世杰, 等.编码成像MLEM互补算法的参数优化[J].哈尔滨工程大学学报, 2021, 42(12):1799-1804. HOU Y W, SONG Y S, SUN S J, et al.Parameter optimization of coded aperture imaging based on the MLEM complementary algorithm[J].Journal of Harbin Engineering University, 2021, 42(12):1799-1804.(in Chinese)
[25] 王悦, 崔雅琦, 於祖庆, 等.基于T样条的变网格等几何薄板动力学分析[J].力学学报, 2021, 53(8):2323-2335. WANG Y, CUI Y Q, YU Z Q, et al.Dynamic analysis of variable mesh isogeometric thin plate based on T-spline[J].Chinese Journal of Theoretical and Applied Mechanics, 2021, 53(8):2323-2335.(in Chinese)

选择文件类型/文献管理软件名称

选择包含的内容